© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 20858
    Prev
    Next
    INDEX
    Explanations

    her children call blessed

    np_acts-logits-general · gemini-2.5-flash-lite

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     importation
    0.47
     δυ
    0.47
     pertes
    0.43
    蒽
    0.43
     מק
    0.43
    σκ
    0.42
     vastly
    0.42
     درجة
    0.42
     capitalize
    0.41
    illions
    0.41
    POSITIVE LOGITS
     negó
    0.48
     iam
    0.48
     Ruta
    0.46
     Saal
    0.45
    ૂત
    0.44
    ्यू
    0.43
     தனது
    0.43
     .:
    0.43
    opadhyay
    0.43
     Been
    0.42
    Activations Density 0.000%

    No Known Activations